paper-with-me

홈 › Papers

Random Policy Enables In-Context Reinforcement Learning within Trust Horizons

2024-10-25 · Weiqin Chen, Santiago Paternain

Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL) emerges when pretraining FMs on decision-making problems in an autoregressive-supervised manner. Nevertheless, current state-of-the-art ICRL algorithms, like Algorithm Distillation, Decision Pretrained Transformer and Decision Importance Transformer, impose stringent requirements on the pretraining dataset concerning the source policies, context information, and action labels. Notably, these algorithms either demand optimal policies or require varying degrees of well-trained behavior policies for all pretraining environments. This significantly hinders the application of ICRL to real-world scenarios, where acquiring optimal or well-trained policies for a substantial volume of real-world training environments can be intractable. To overcome this challenge, we introduce a novel approach, termed State-Action Distillation (SAD), that allows to generate an effective pretraining dataset guided solely by random policies. In particular, SAD selects query states and corresponding action labels by distilling outstanding state-action pairs from the entire state and action spaces by using random policies within a trust horizon, and then inherits the classical autoregressive-supervised mechanism during pretraining. To the best of our knowledge, this is the first work that enables effective ICRL under random policies and random contexts. We also establish quantitative analysis of the trustworthiness as well as the performance guarantees of SAD. Moreover, our empirical results across multiple popular ICRL benchmark environments demonstrate that, on average, SAD outperforms the best baseline by 236.3% in the offline evaluation and by 135.2% in the online evaluation.

📄 PDF Abstract BibTeX arXiv:2410.19982

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context LearningIn-Context Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Zero-shot Generalization

Methods 이 논문이 사용한 방법론

Six Ways To Communicate To Someone At Expedia Via Phone And Email's. To communicate or get human at Expedia, the quickest option is typically to call their customer service at +1-888-829-0881 or +1(805) 330 (4056). You can also use the live chat…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…

Similar Papers 제목 키워드 기반

Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment

2026-05-26 · Gengyue Han, Yiheng Feng arxiv

Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real wor…

Reinforcement LearningAutonomous Vehicles

Exploratory Optimal Stopping: A Singular Control Formulation

2024-08-18 · Jodi Dianetti, Giorgio Ferrari, Renyuan Xu

This paper explores continuous-time and state-space optimal stopping problems from a reinforcement learning perspective. We begin by formulating the stopping problem using randomized stopping times, where the decision ma…

reinforcement-learningReinforcement Learning

HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation

2026-02-04 · Puyue Wang, Jiawei Hu, Yan Gao, Junyan Wang 외 arxiv

Humanoid robots can suffer significant performance drops under small changes in dynamics, task specifications, or environment setup. We propose HoRD, a two-stage learning framework for robust humanoid control under domai…

Reinforcement Learning

Episodic Policy Gradient Training

2021-12-03 · Hung Le, Majid Abdolshah, Thommen K. George, Kien Do 외

We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, w…

Policy Gradient MethodsScheduling

On Reward Transferability in Adversarial Inverse Reinforcement Learning: Insights from Random Matrix Theory

2024-10-10 · Yangchun Zhang, Wang Zhou, Yirui Zhou

In the context of inverse reinforcement learning (IRL) with a single expert, adversarial inverse reinforcement learning (AIRL) serves as a foundational approach to providing comprehensive and transferable task descriptio…

reinforcement-learningReinforcement Learning